boiwsa is an R package for the seasonal adjustment and forecasting of weekly time series data. It offers a user-friendly interface for computing seasonally adjusted estimates and includes diagnostic tools to assess the quality of the adjustments.
wex is an R package for computing the exact observation weights for the Kalman filter and smoother, based on the method proposed by Koopman and Harvey (2003). It facilitates in-depth analysis of state-space models, helping researchers and practitioners extract meaningful insights from time series data. The package is especially valuable in dynamic factor models, where the computed weights enable decomposition of individual variables’ contributions to latent factors.
cforecast is an R package for conducting conditional forecasts and scenario analysis using vector autoregressive (VAR) models. It implements the Kalman filtering methodology proposed by Clarida and Coyle (1984) and Banbura, Giannone, and Lenza (2015), allowing users to simulate forecast paths under imposed constraints on future values of selected variables.
[GitHub]
Ginker, T., Ilek, A., and Snir, A. (2024). Rigidity and Synchronization: Analyzing Online and Offline Price Dynamics.
A GitHub repo with a replication code for our method of computing the benchmark for the index of price synchronization under the null hypothesis of no coordination (i.e. independence) between the stores.